Anas

I’ve decided to leave my home in a couple of days. I’ll try to save money for a few months and won’t be able to afford tokens. I’ll miss Factory Ai and Codex. I’ll come back once this homeless era ends.

@connorado @nicolaygerold @AmpCode It’s similar to GPT-5.5 xhigh, like how we use it in the Codex CLI?

@anasibnanwar @nicolaygerold @AmpCode It's a mode in Amp that leverages GPT 5.5 with deep reasoning and extended thinking. You can see what other modes you can use here: ampcode.com/models

It's finally here. `deep` is now using GPT 5.5 in @AmpCode.

A soldier died during the war. It was a massive clean-up effort removing over 100,000 lines of slop documents and several thousand lines of code. It was good stuff.

@KingBootoshi x.com/anasibnanwar/s…

anybody who seriously uses AI at this point deeply understands this shit is not replacing humans in anything because we are all working 10x more since we are 10x more productive everyone is just going to operate at a new layer that was never seen before and it's MARVELOUS

@skeptrune @sama People who are good at prompting 5.5 have more girlfriends and sex appeal than the ones who use Claude

new study finds that Gen Z prefers prompting codex 5-5 over having sex (per @sama)

@EnoReyes Any help?

@FactoryAI In Mission Control, can you clarify something? When I manually compress a chat, it opens a new chat window and displays a message saying “loaded summary from session X.” Is this new chat intended to function as a genuine continuation of the original session, or is it merely using a summary or reference from the previous one? In Codex-style compression, the same chat persists with a compacted context window. Therefore, I’m curious to understand how Factory compression operates during an active mission. Does switching or compressing the chat mid-mission degrade orchestration quality, lose state, or impact agent coordination? If I want to modify the orchestrator model or compress the context during a Mission Control run without disrupting the mission, what’s the recommended workflow?

@catalinmpit Never switch back to Claude.

Now that I have the ChatGPT Pro plan, give me your best Codex tips and tricks.

@benln Skeina.tech is building Factory for accountants. It allows you to manage your accounts while you focus on operations and execution. I’m working on this project solo.

Kicked off a group chat for Cursor team members who occasionally angel invest. There are now 20 of us. Reach out if you're working on something new, love to share with the group!

@zaidmukaddam @FactoryAI has banned useEffect in their harness

it's always a useEffect that breaks your code

I’ve coined a word for when we don’t have enough tokens to build something: “Token Broke” Guess what? I’m token broke now. :(

@robinebers @cursor_ai How much usage do we get in cursor of Opus 4.7 in the ultra plan?

i'm telling you, opus 4.7 is hella underrated yes it has it's problems, especially long context but holy shit does it hit hard in @cursor_ai 🤯 i've rarely built this much in a single day

It’s unfortunate that the person never tried @FactoryAI and then reached this conclusion. The true value lies not just in limitations or raw pricing. Tools like @FactoryAI @cursor_ai truly shine through their environment, rapid feature updates, and workflow optimisations that significantly speed up shipping code, even under tighter quotas. It’s the complete harness that boosts productivity, not just the underlying model access.

CURSOR AND COPILOT ARE ABOUT TO DIE developer spent 3 months testing Claude Code, Codex and Cursor in parallel, the result? he exhausted the Cursor usage quota in a couple of weeks. then you sit and wait or pay extra while Claude Code and Codex reset the limits weekly. for the same price and here's the question that no one wants to ask out loud: why are you still paying for cursor or copilot when Claude Code and Codex give you the same amount or even more? this isn't just about pricing. this is a survival question for entire companies think about it: - Cursor, Copilot, and Windsurf all resell other people's models with a wrapper - Anthropic and OpenAI sell THEIR OWN models directly - and do it cheaper It's like trying to compete with a factory by buying parts from the same factory what should actually scare these companies: - Claude Code runs straight from the terminal, no IDE needed - Codex from OpenAI - same thing - both reset limits more often - both evolve faster the developer literally asks: 'is there even room for another coding agent in this market?' and the honest answer is - probably not we are witnessing a classic scenario: platforms devour their intermediaries Claude Code did the same thing without subscribing to a separate editor I'm not saying that Сursor will die tomorrow. but if your business model is to resell someone else's API at a premium, you should be nervous the question is not 'Cursor vs Claude Code', but: how many months do wrapper companies have left before model providers take over the entire market?

@ajambrosino Mission Control similar to Factory droids

what should we do in the next 3 months?

Show us your pets!! We’re picking the 10 favorites for 30 days of ChatGPT pro!

Show us the Codex pets you hatched. Use /hatch to create your own Codex pet. We’ll pick 10 favorites to get 30 days of ChatGPT Pro.

@kapilansh_twt What do you guys expect in 20$?

hot take Cursor has the worst $20 plan of any AI coding tool Claude Code - clear limits Codex - clear limits Cursor Pro - extended limits extended of what nobody knows am I the only one bothered by this

What’s the best way to brainstorm product names?

@ItsAlexhere0 Codex

Is there any trick to avoid Claude Code usage limits?

@SIGKITTEN @yacineMTB I tried using it but idk why i am unable to connect to my pc

why tf isnt @yacineMTB using my kitty app